Ziyi Zhang

Ziyi Zhang

Auto-generated profile, based on publicly available information

Ziyi Zhang

National Engineering Research Center for Multimedia Software, School of Computer Science, Hubei Luojia Laboratory, Wuhan University, Wuhan, Hubei, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 February 2023 in IEEE Transactions on Affective Computing
Verified
Journal Article
Closed access
QSQingHongYa Shi
QingHongYa Shi
Mang YeMang Ye
Mang Ye
ZZZiyi Zhang
Ziyi Zhang
BDBo Du
Bo Du
Visual intention understanding is to mine the potential and subjective intention behind the images, which includes the user's hidden emotions and perspectives. Due to the label ambiguity, this paper presents a novel learnable Hierarchical Label Embedding and Grouping (HLEG). It is featured in three aspects: 1) For effectively mining the underlying meaning of images, we build a hierarchical transformer structure to model the hierarchy of labels, formulating a multi-level classification scheme. 2) For the label ambiguity issue, we design a novel learnable label embedding with accumulative grouping integrated into the hierarchical structure, which does not require additional annotation. 3) For multi-level classification, we propose a “Hard-First” optimization strategy to adaptively adjust the classification optimization at different levels, avoiding over-classification of the coarse labels. HLEG enhances the F1 score (average +1.24%) and mAP (average +1.48%) on Intentonomy over prominent baseline models. Comprehensive experiments validate the superiority of our proposed method, achieving state-of-the-art performance under various settings. Code is available at https://github.com/ShiQingHongYa/HLEG .

1 May 2021
Verified
Conference Paper
Open access
ASA. W. Seal
A. W. Seal
MBMary Carlos Bernal-Cárdenas
Mary Carlos Bernal-Cárdenas
MCMary Caulo
Mary Caulo
NCNathan Cooper
Nathan Cooper
WMWilliam Mary
William Mary
ZZZiyi Zhang
Ziyi Zhang
The conference offers a note of thanks and lists its reviewers.

1 November 2023 in arXiv
Verified
Preprint
Open access
PDF file
SASaurabh Agarwal
Saurabh Agarwal
CYChengpo Yan
Chengpo Yan
ZZZiyi Zhang
Ziyi Zhang
SVShivaram Venkataraman
Shivaram Venkataraman
Deep learning based recommendation models (DLRM) are widely used in several business critical applications. Training such recommendation models efficiently is challenging because they contain billions of embedding-based parameters, leading to significant overheads from embedding access. By profiling existing systems for DLRM training, we observe that around 75\% of the iteration time is spent on embedding access and model synchronization. Our key insight in this paper is that embedding access has a specific structure which can be used to accelerate training. We observe that embedding accesses are heavily skewed, with around 1\% of embeddings representing more than 92\% of total accesses. Further, we observe that during offline training we can lookahead at future batches to determine exactly which embeddings will be needed at what iteration in the future. Based on these insights, we develop Bagpipe, a system for training deep recommendation models that uses caching and prefetching to overlap remote embedding accesses with the computation. We design an Oracle Cacher, a new component that uses a lookahead algorithm to generate optimal cache update decisions while providing strong consistency guarantees against staleness. We also design a logically replicated, physically partitioned cache and show that our design can reduce synchronization overheads in a distributed setting. Finally, we propose a disaggregated system architecture and show that our design can enable low-overhead fault tolerance. Our experiments using three datasets and four models show that Bagpipe provides a speed up of up to 5.6x compared to state of the art baselines, while providing the same convergence and reproducibility guarantees as synchronous training.